Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3189 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.6915. Min Range: -3.6915

Max Act: 3.6915. Min Act: -0.0000

Data Index: 104991 (C4 (Web Text))

Max Activating Token Index: 256

Text #1

Max Range: 3.6915. Min Range: -3.6915

Max Act: 3.5278. Min Act: -0.0000

Data Index: 1104181 (C4 (Web Text))

Max Activating Token Index: 63

Text #2

Max Range: 3.6915. Min Range: -3.6915

Max Act: 3.0651. Min Act: -0.0000

Data Index: 623631 (C4 (Web Text))

Max Activating Token Index: 317

Text #3

Max Range: 3.6915. Min Range: -3.6915

Max Act: 3.2014. Min Act: -0.0000

Data Index: 621704 (C4 (Web Text))

Max Activating Token Index: 723

Text #4

Max Range: 3.6915. Min Range: -3.6915

Max Act: 3.0998. Min Act: -0.0000

Data Index: 210093 (C4 (Web Text))

Max Activating Token Index: 451

Text #5

Max Range: 3.6915. Min Range: -3.6915

Max Act: 3.0850. Min Act: -0.0000

Data Index: 336186 (C4 (Web Text))

Max Activating Token Index: 640

Text #6

Max Range: 3.6915. Min Range: -3.6915

Max Act: 2.7972. Min Act: -0.0000

Data Index: 1057461 (C4 (Web Text))

Max Activating Token Index: 261

Text #7

Max Range: 3.6915. Min Range: -3.6915

Max Act: 2.7571. Min Act: -0.0000

Data Index: 90406 (C4 (Web Text))

Max Activating Token Index: 736

Text #8

Max Range: 3.6915. Min Range: -3.6915

Max Act: 2.8726. Min Act: -0.0000

Data Index: 520440 (C4 (Web Text))

Max Activating Token Index: 735

Text #9

Max Range: 3.6915. Min Range: -3.6915

Max Act: 2.7815. Min Act: -0.0000

Data Index: 164090 (C4 (Web Text))

Max Activating Token Index: 922

Text #10

Max Range: 3.6915. Min Range: -3.6915

Max Act: 2.5049. Min Act: -0.0000

Data Index: 837992 (C4 (Web Text))

Max Activating Token Index: 543

Text #11

Max Range: 3.6915. Min Range: -3.6915

Max Act: 2.6283. Min Act: -0.0000

Data Index: 1132324 (C4 (Web Text))

Max Activating Token Index: 831

Text #12

Max Range: 3.6915. Min Range: -3.6915

Max Act: 2.6044. Min Act: -0.0001

Data Index: 872135 (C4 (Web Text))

Max Activating Token Index: 988

Text #13

Max Range: 3.6915. Min Range: -3.6915

Max Act: 2.7169. Min Act: -0.0000

Data Index: 1330842 (C4 (Web Text))

Max Activating Token Index: 788

Text #14

Max Range: 3.6915. Min Range: -3.6915

Max Act: 2.7204. Min Act: -0.0000

Data Index: 15738 (C4 (Web Text))

Max Activating Token Index: 254

Text #15

Max Range: 3.6915. Min Range: -3.6915

Max Act: 2.5548. Min Act: -0.0000

Data Index: 1176410 (C4 (Web Text))

Max Activating Token Index: 569

Text #16

Max Range: 3.6915. Min Range: -3.6915

Max Act: 2.7903. Min Act: -0.0000

Data Index: 81218 (C4 (Web Text))

Max Activating Token Index: 214

Text #17

Max Range: 3.6915. Min Range: -3.6915

Max Act: 2.2643. Min Act: -0.0000

Data Index: 655418 (C4 (Web Text))

Max Activating Token Index: 613

Text #18

Max Range: 3.6915. Min Range: -3.6915

Max Act: 2.4866. Min Act: -0.0000

Data Index: 1198603 (C4 (Web Text))

Max Activating Token Index: 359

Text #19

Max Range: 3.6915. Min Range: -3.6915

Max Act: 2.5922. Min Act: -0.0000

Data Index: 173926 (C4 (Web Text))

Max Activating Token Index: 148